Context1M tokens
Input price$0.15 / M tokens
Output price$0.6 / M tokens
CreatedSep 10, 2026
Original-vendor pricing · Standard API · USD per million text tokens. Off-peak non-cached prices. Peak price: $0.30 input / $1.20 output per million, Mon-Fri 01:00-04:00 and 06:00-10:00 UTC, excluding Chinese public holidays. Legacy Flash API aliases now serve V4.1 Flash 1017.
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
About DeepSeek V4.1 Flash
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
Modalities
text, imagetext